{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Draws some Box Plot diagrams on data distribution"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### NuGet package installation"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"Installing package Microsoft.ML, version 1.4.0.............done!"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"Successfully added reference to package Microsoft.ML, version 1.4.0"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"Installing package XPlot.Plotly, version 3.0.1.....done!"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"Successfully added reference to package XPlot.Plotly, version 3.0.1"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"#r \"nuget:Microsoft.ML, 1.4.0\"\n",
"#r \"nuget:XPlot.Plotly, 3.0.1\""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Namespaces"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"using Microsoft.ML;\n",
"using Microsoft.ML.Data;\n",
"using XPlot.Plotly;"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Simple start: well prepared data"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Read the raw data"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"var mlContext = new MLContext(seed: null);\n",
"\n",
"var reader = mlContext.Data.CreateTextLoader(\n",
" new TextLoader.Options()\n",
" {\n",
" Separators = new[] { ',' },\n",
" HasHeader = true,\n",
" Columns = new[]\n",
" {\n",
" new TextLoader.Column(\"Age\", DataKind.Single, 2),\n",
" new TextLoader.Column(\"AnnualIncome\", DataKind.Single, 3),\n",
" new TextLoader.Column(\"SpendingScore\", DataKind.Single, 4),\n",
" }\n",
" });\n",
" \n",
"var dataView = reader.Load(\"./Mall_Customers.csv\");"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Visualize the data"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"var graph = new Graph.Box()\n",
"{\n",
" y = dataView.GetColumn(dataView.Schema[0]),\n",
" name = \"Age\"\n",
"};\n",
"\n",
"var graph2 = new Graph.Box()\n",
"{\n",
" y = dataView.GetColumn(dataView.Schema[1]),\n",
" name = \"Annual Income\"\n",
"};\n",
"\n",
"var graph3 = new Graph.Box()\n",
"{\n",
" y = dataView.GetColumn(dataView.Schema[2]),\n",
" name = \"Spending Score\"\n",
"};\n",
"\n",
"var chart = Chart.Plot(new List { graph, graph2, graph3 });\n",
"\n",
"var layout = new Layout.Layout(){ title=\"Shopping Mall Customers Data Distribution\", showlegend = false };\n",
"chart.WithLayout(layout);\n",
"\n",
"display(chart);"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## A more interesting sample: dispersed data"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Read the raw data"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"var reader2 = mlContext.Data.CreateTextLoader(\n",
" new TextLoader.Options()\n",
" {\n",
" Separators = new[] { ',' },\n",
" HasHeader = true,\n",
" Columns = new[]\n",
" {\n",
" new TextLoader.Column(\"Ts\", DataKind.Single, 9),\n",
" new TextLoader.Column(\"Orb\", DataKind.Single, 12),\n",
" new TextLoader.Column(\"Drb\", DataKind.Single, 13),\n",
" new TextLoader.Column(\"Trb\", DataKind.Single, 14),\n",
" new TextLoader.Column(\"Ast\", DataKind.Single, 15),\n",
" new TextLoader.Column(\"Stl\", DataKind.Single, 16),\n",
" new TextLoader.Column(\"Blk\", DataKind.Single, 17),\n",
" new TextLoader.Column(\"Tov\", DataKind.Single, 18),\n",
" new TextLoader.Column(\"Usg\", DataKind.Single, 19),\n",
" new TextLoader.Column(\"Age\", DataKind.Single, 4)\n",
" }\n",
" });\n",
"\n",
"var dataView2 = reader2.Load(\"./2017-18_NBA_salary.csv\");"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Visualize the data"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"var chart2 = Chart.Plot(new List \n",
"{ \n",
" new Graph.Box()\n",
" {\n",
" y = dataView2.GetColumn(dataView2.Schema[0]),\n",
" name = \"True Shootings\"\n",
" },\n",
" new Graph.Box()\n",
" {\n",
" y = dataView2.GetColumn(dataView2.Schema[1]),\n",
" name = \"Offensive Rebounds\"\n",
" },\n",
" new Graph.Box()\n",
" {\n",
" y = dataView2.GetColumn(dataView2.Schema[2]),\n",
" name = \"Defensive Rebounds\"\n",
" },\n",
" new Graph.Box()\n",
" {\n",
" y = dataView2.GetColumn(dataView2.Schema[3]),\n",
" name = \"Team Rebounds\"\n",
" },\n",
" new Graph.Box()\n",
" {\n",
" y = dataView2.GetColumn(dataView2.Schema[4]),\n",
" name = \"Assists\"\n",
" }, \n",
" new Graph.Box()\n",
" {\n",
" y = dataView2.GetColumn(dataView2.Schema[5]),\n",
" name = \"Steals\"\n",
" },\n",
" new Graph.Box()\n",
" {\n",
" y = dataView2.GetColumn(dataView2.Schema[6]),\n",
" name = \"Blocks\"\n",
" },\n",
" new Graph.Box()\n",
" {\n",
" y = dataView2.GetColumn(dataView2.Schema[7]),\n",
" name = \"Turnover\"\n",
" },\n",
" new Graph.Box()\n",
" {\n",
" y = dataView2.GetColumn(dataView2.Schema[8]),\n",
" name = \"Usage\"\n",
" },\n",
" new Graph.Box()\n",
" {\n",
" y = dataView2.GetColumn(dataView2.Schema[9]),\n",
" name = \"Age\"\n",
" }\n",
"});\n",
"\n",
"var layout2 = new Layout.Layout(){ title=\"NBA Statistics Data Distribution\", showlegend = false };\n",
"chart2.WithLayout(layout2);\n",
"\n",
"display(chart2);"
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".NET (C#)",
"language": "C#",
"name": ".net-csharp"
},
"language_info": {
"file_extension": ".cs",
"mimetype": "text/x-csharp",
"name": "C#",
"pygments_lexer": "csharp",
"version": "8.0"
}
},
"nbformat": 4,
"nbformat_minor": 2
}